Document-level retrieval eval datasets built for the Citras per-domain benchmark.
Bo Wang
bowang0911
AI & ML interests
None yet
Recent Activity
new activity about 4 hours ago
bowang0911/Nano-35B-A3B-128K:Add a trainable 6/24/6 recurrent core with iteration-specific KV caches new activity about 4 hours ago
bowang0911/Nano-35B-A3B-128K:Use 36 independent layers and 1280-wide experts for the main architecture candidate updated a model about 5 hours ago
bowang0911/Nano-35B-A3B-128K